© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 118911
    Prev
    Next
    INDEX
    Explanations

    commotion, stir, uproar, noise

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects words that denote commotion or noisy disturbance (e.g., synonyms for “ruckus,” “uproar,” “brouhaha,” “hoopla,” or “fuss”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setiap
    -1.84
    
    -1.70
    𓍊
    -1.58
     aidant
    -1.48
     perpé
    -1.48
     σας
    -1.41
    anah
    -1.38
    沁
    -1.38
     speranza
    -1.38
     diğer
    -1.38
    POSITIVE LOGITS
     about
    2.42
     fuss
    1.95
     commotion
    1.91
     it
    1.91
    </strong>
    1.88
     tumult
    1.51
     upheaval
    1.46
    ांकि
    1.40
    さまで
    1.37
    áme
    1.33
    Activations Density 0.030%

    No Known Activations